ALIF EXPLORATION
Selected Variables
base: Code of the patient
covariates:
- Age
- Gender
- Prior Spine Surgery
- '1st surgeon: experience in ASD surgery'
- ASA classification
- Decompression
- Osteotomy
- 3CO
- SPOs
- BMI_First Visit
- Tobacco use_First Visit
- Osteoporosis / osteopenia
- Levels Previously operated - Lower
- LGap
- RLL
- Number of Interbody Fusions
- 'Posterior Instrumented Fusion: Upper / Lower Levels'
- Alif
- LL-Lordosis Difference
outcomes_ql:
- 2Y. ODI - Score (%)
- 2Y. SRS22 - SRS Subtotal score
- 2Y. SF36 - MCS
- 2Y. SF36 - PCS
outcomes_radiology:
- 6W. Major curve Cobb angle
- 1Y. Major curve Cobb angle
- 6W. T1 Sagittal Tilt
- 1Y. T1 Sagittal Tilt
- 6W. Sagittal Balance
- 1Y. Sagittal Balance
- 6W. Global Tilt
- 1Y. Global Tilt
- 6W. Lordosis (top of L1-S1)
- 1Y. Lordosis (top of L1-S1)
- 6W. LGap
- 1Y. LGap
- 6W. Pelvic Tilt
- 1Y. Pelvic Tilt
predictive:
- Weight (kgs)_First Visit
- Height (cm)_First Visit
- Total surgical time st1+st2+st3
- Osteotomy
- Alcohol/drug abuse
- Anemia or other blood disorders
- Osteoarthritis
- Mild vascular
- Depression / anxiety
- Diabetes with end organ damage
- Cardiac
- Hypertension
- Chronic pulmonary disease
- Nervous system disorders
- Renal
- Peripheral vascular disease
- Psychiatric / Behavioral
- Peptic ulcer
- Bladder incontinence
- Bowel incontinence
- Leg weakness
- Loss of balance
- NRS back - Leg pain - Average
- Tobacco use_First Visit
- Years with spine problems
- ODI - Score (%)_First Visit
- SRS22 - SRS Total score_First Visit
- SF36 - PCS_First Visit
- SF36 - MCS_First Visit
- Major curve Cobb angle
demographic:
- Age
- Gender
- Prior Spine Surgery
- ASA classification
- 3CO
- BMI_First Visit
- Global Tilt
- Ideal LL
- Lordosis (top of L1-S1)
- ODI - Score (%)_First Visit
- SRS22 - SRS Total score_First Visit
- SF36 - PCS_First Visit
- SF36 - MCS_First Visit
- Major curve Cobb angle
expanded:
- Age
- Gender
- Prior Spine Surgery
- '1st surgeon: experience in ASD surgery'
- ASA classification
- Decompression
- Osteotomy
- 3CO
- SPOs
- BMI_First Visit
- Tobacco use_First Visit
- Osteoporosis / osteopenia
- Levels Previously operated - Lower
- LGap
- RLL
- Number of Interbody Fusions
- 'Posterior Instrumented Fusion: Upper / Lower Levels'
- Alif
- LL-Lordosis Difference
- Weight (kgs)_First Visit
- Height (cm)_First Visit
- Total surgical time st1+st2+st3
- Alcohol/drug abuse
- Anemia or other blood disorders
- Osteoarthritis
- Mild vascular
- Depression / anxiety
- Diabetes with end organ damage
- Cardiac
- Hypertension
- Chronic pulmonary disease
- Nervous system disorders
- Renal
- Peripheral vascular disease
- Psychiatric / Behavioral
- Peptic ulcer
- Bladder incontinence
- Bowel incontinence
- Leg weakness
- Loss of balance
- NRS back - Leg pain - Average
- Years with spine problems
- ODI - Score (%)_First Visit
- SRS22 - SRS Total score_First Visit
- SF36 - PCS_First Visit
- SF36 - MCS_First Visit
- Major curve Cobb angle
- SRS22 - SRS Subtotal score_First Visit
- T1 Sagittal Tilt
- Sagittal Balance
- Global Tilt
- Lordosis (top of L1-S1)
- Pelvic TiltPropensity Scores Common Support
## Loading required package: lattice##
## Attaching package: 'lattice'## The following object is masked from 'package:boot':
##
## melanoma##
## Attaching package: 'caret'## The following object is masked from 'package:survival':
##
## clusterModel Stats
- Treatment proportion: 0.127
- Model Type: elastic_net
- Accuracy: 0.8983651
- Params: alpha: 0.4923077 lambda: 0.0016797
Model Coefficients
Bootstraping replicas: 200, confidence intervals at 95% level
Average Treatment Effects - Quality Life
Outcome: 2Y. ODI - Score (%)
Distribution:
0% 25% 50% 75% 100%
-67 -27 -14 -4 40
Model Type Y: boosting
RMSE: 18.4627137838729
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5357143
Model Type No: boosting
RMSE: 17.6070112099825
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.6071429
ATE (Yes-No): 0.772 (Std.Error: 2.326)
Trimmed ATE (Yes-No): 0.828 (Std.Error: 2.435)
Upper ATE (Yes-No): -0.591 (Std.Error: 2.925)
Observational differences in treatment 4.93 (Yes-No)
treatment outcome
1: Yes 35.62069
2: No 30.69076`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 2Y. SRS22 - SRS Subtotal score
Distribution:
0% 25% 50% 75% 100%
-0.95 0.21 0.70 1.16 3.05
Model Type Y: boosting
RMSE: 0.703247813683134
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.6785714
Model Type No: boosting
RMSE: 0.691979555657921
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5357143
ATE (Yes-No): 0.225 (Std.Error: 0.067)
Trimmed ATE (Yes-No): 0.22 (Std.Error: 0.07)
Upper ATE (Yes-No): 0.334 (Std.Error: 0.135)
Observational differences in treatment -0.024 (Yes-No)
treatment outcome
1: Yes 3.347241
2: No 3.371548`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 2Y. SF36 - MCS
Distribution:
0% 25% 50% 75% 100%
-33.82 -3.72 3.85 12.91 39.74
Model Type Y: boosting
RMSE: 18.2094690038809
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
Model Type No: boosting
RMSE: 12.2253370419963
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.9642857
ATE (Yes-No): -1.596 (Std.Error: 0.079)
Trimmed ATE (Yes-No): -2.04 (Std.Error: 0.071)
Upper ATE (Yes-No): 9.558 (Std.Error: 0.708)
Observational differences in treatment -1.046 (Yes-No)
treatment outcome
1: Yes 45.83280
2: No 46.87847`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 2Y. SF36 - PCS
Distribution:
0% 25% 50% 75% 100%
-18.94 0.61 6.57 12.42 38.99
Model Type Y: boosting
RMSE: 8.75377298281998
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.8214286
Model Type No: boosting
RMSE: 9.34705399966407
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.8571429
ATE (Yes-No): 1.171 (Std.Error: 0.514)
Trimmed ATE (Yes-No): 1.548 (Std.Error: 0.528)
Upper ATE (Yes-No): -8.307 (Std.Error: 1.266)
Observational differences in treatment -2.2 (Yes-No)
treatment outcome
1: Yes 38.04520
2: No 40.24513`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Average Treatment Effects - Radiology
Outcome: 6W. Major curve Cobb angle
Distribution:
0% 25% 50% 75% 100%
-72.00 -21.00 -10.63 -4.00 30.80
Model Type Y: boosting
RMSE: 21.1366893988911
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
Model Type No: boosting
RMSE: 13.1468502299874
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.6785714
ATE (Yes-No): -0.253 (Std.Error: 0.262)
Trimmed ATE (Yes-No): -0.111 (Std.Error: 0.255)
Upper ATE (Yes-No): -3.655 (Std.Error: 1.519)
Observational differences in treatment 3.397 (Yes-No)
treatment outcome
1: Yes 25.23682
2: No 21.83957`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. Major curve Cobb angle
Distribution:
0% 25% 50% 75% 100%
-64.00 -22.47 -10.10 -3.00 22.44
Model Type Y: boosting
RMSE: 20.4606579214263
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
Model Type No: boosting
RMSE: 14.0988713620794
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.6428571
ATE (Yes-No): -1.136 (Std.Error: 0.238)
Trimmed ATE (Yes-No): -1.001 (Std.Error: 0.239)
Upper ATE (Yes-No): -4.044 (Std.Error: 1.46)
Observational differences in treatment 2.873 (Yes-No)
treatment outcome
1: Yes 23.74424
2: No 20.87154`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. T1 Sagittal Tilt
Distribution:
0% 25% 50% 75% 100%
-23.631420 -6.000000 -1.496444 1.722212 18.000000
Model Type Y: boosting
RMSE: 6.54048994832397
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
Model Type No: boosting
RMSE: 6.08946309021792
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
ATE (Yes-No): -5.319 (Std.Error: 0)
Trimmed ATE (Yes-No): -5.426 (Std.Error: 0)
Upper ATE (Yes-No): -2.693 (Std.Error: 0)
Observational differences in treatment -1.028 (Yes-No)
treatment outcome
1: Yes -3.468840
2: No -2.441266`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. T1 Sagittal Tilt
Distribution:
0% 25% 50% 75% 100%
-30.098675 -6.000000 -2.009266 1.134408 20.000000
Model Type Y: boosting
RMSE: 7.53436331085143
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.7142857
Model Type No: boosting
RMSE: 5.92501849428631
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5714286
ATE (Yes-No): -3.398 (Std.Error: 0.543)
Trimmed ATE (Yes-No): -3.353 (Std.Error: 0.569)
Upper ATE (Yes-No): -4.187 (Std.Error: 1.201)
Observational differences in treatment -0.702 (Yes-No)
treatment outcome
1: Yes -3.307045
2: No -2.605153`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. Sagittal Balance
Distribution:
0% 25% 50% 75% 100%
-194.7900 -69.0225 -27.8500 1.9650 114.1500
Model Type Y: boosting
RMSE: 63.1092408321018
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.7142857
Model Type No: boosting
RMSE: 53.7765206378945
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5714286
ATE (Yes-No): -43.892 (Std.Error: 3.255)
Trimmed ATE (Yes-No): -44.361 (Std.Error: 3.405)
Upper ATE (Yes-No): -34.415 (Std.Error: 9.738)
Observational differences in treatment -8.555 (Yes-No)
treatment outcome
1: Yes 26.17093
2: No 34.72625`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. Sagittal Balance
Distribution:
0% 25% 50% 75% 100%
-237.470 -67.310 -30.510 5.985 109.540
Model Type Y: boosting
RMSE: 73.0757122069807
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5714286
Model Type No: boosting
RMSE: 52.9599213723664
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.7857143
ATE (Yes-No): -37.127 (Std.Error: 4.449)
Trimmed ATE (Yes-No): -36.309 (Std.Error: 4.732)
Upper ATE (Yes-No): -52.294 (Std.Error: 8.166)
Observational differences in treatment -12.482 (Yes-No)
treatment outcome
1: Yes 25.00806
2: No 37.48991`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. Global Tilt
Distribution:
0% 25% 50% 75% 100%
-68.620 -18.035 -6.000 1.610 149.410
Model Type Y: boosting
RMSE: 14.769757504468
Params: nrounds: 50.0
max_depth: 14
eta: 0.4
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5357143
Model Type No: boosting
RMSE: 14.6872937338084
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.6785714
ATE (Yes-No): -12.407 (Std.Error: 0.448)
Trimmed ATE (Yes-No): -12.666 (Std.Error: 0.46)
Upper ATE (Yes-No): -6.455 (Std.Error: 1.493)
Observational differences in treatment -5.722 (Yes-No)
treatment outcome
1: Yes 19.65955
2: No 25.38121`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. Global Tilt
Distribution:
0% 25% 50% 75% 100%
-62.63 -16.94 -6.21 1.00 26.00
Model Type Y: boosting
RMSE: 15.4648373229717
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5714286
Model Type No: boosting
RMSE: 11.6483897787846
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
ATE (Yes-No): -13.593 (Std.Error: 1.351)
Trimmed ATE (Yes-No): -13.53 (Std.Error: 1.431)
Upper ATE (Yes-No): -14.843 (Std.Error: 1.512)
Observational differences in treatment -5.435 (Yes-No)
treatment outcome
1: Yes 20.46031
2: No 25.89494`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. Lordosis (top of L1-S1)
Distribution:
0% 25% 50% 75% 100%
-94.930 -24.000 -9.635 0.140 29.000
Model Type Y: boosting
RMSE: 20.2872774490426
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
RMSE: 15.8674179095648
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5357143
ATE (Yes-No): -5.975 (Std.Error: 1.587)
Trimmed ATE (Yes-No): -6.064 (Std.Error: 1.656)
Upper ATE (Yes-No): -3.838 (Std.Error: 3.06)
Observational differences in treatment -1.998 (Yes-No)
treatment outcome
1: Yes -51.05795
2: No -49.05961`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. Lordosis (top of L1-S1)
Distribution:
0% 25% 50% 75% 100%
-94.630 -25.000 -8.230 -0.015 23.380
Model Type Y: boosting
RMSE: 22.5947910024884
Params: nrounds: 100.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.6071429
Model Type No: boosting
RMSE: 15.7011649949062
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.9285714
ATE (Yes-No): -13.388 (Std.Error: 1.599)
Trimmed ATE (Yes-No): -13.293 (Std.Error: 1.68)
Upper ATE (Yes-No): -15.438 (Std.Error: 2.022)
Observational differences in treatment 0.145 (Yes-No)
treatment outcome
1: Yes -49.32812
2: No -49.47321`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. LGap
Distribution:
0% 25% 50% 75% 100%
-96.1234 -24.0000 -9.1601 0.4592 78.9200
Model Type Y: boosting
RMSE: 20.5980085555759
Params: nrounds: 100.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.75
Model Type No: boosting
RMSE: 17.3197054268944
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.7857143
ATE (Yes-No): -5.681 (Std.Error: 0.948)
Trimmed ATE (Yes-No): -5.596 (Std.Error: 1.007)
Upper ATE (Yes-No): -7.724 (Std.Error: 1.893)
Observational differences in treatment -3.364 (Yes-No)
treatment outcome
1: Yes 11.29544
2: No 14.65980`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. LGap
Distribution:
0% 25% 50% 75% 100%
-94.8082 -25.0000 -8.5790 -0.1606 22.0800
Model Type Y: boosting
RMSE: 24.4436751231924
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.9285714
Model Type No: boosting
RMSE: 15.6874869377557
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 1.0
ATE (Yes-No): -13.325 (Std.Error: 0.866)
Trimmed ATE (Yes-No): -13.179 (Std.Error: 0.918)
Upper ATE (Yes-No): -16.447 (Std.Error: 0.833)
Observational differences in treatment -2.197 (Yes-No)
treatment outcome
1: Yes 11.43743
2: No 13.63423`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 6W. Pelvic Tilt
Distribution:
0% 25% 50% 75% 100%
-36.41 -8.59 -2.53 2.11 14.42
Model Type Y: boosting
RMSE: 10.0995449989016
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.7142857
Model Type No: boosting
RMSE: 7.56723206016123
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): -3.416 (Std.Error: 0.76)
Trimmed ATE (Yes-No): -3.378 (Std.Error: 0.793)
Upper ATE (Yes-No): -4.4 (Std.Error: 1.538)
Observational differences in treatment -3.393 (Yes-No)
treatment outcome
1: Yes 18.57233
2: No 21.96521`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: 1Y. Pelvic Tilt
Distribution:
0% 25% 50% 75% 100%
-26.620 -7.160 -2.205 1.945 23.000
Model Type Y: boosting
RMSE: 10.9277782855396
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.9285714
Model Type No: boosting
RMSE: 6.79640772025747
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.75
ATE (Yes-No): -7.714 (Std.Error: 0.428)
Trimmed ATE (Yes-No): -7.938 (Std.Error: 0.45)
Upper ATE (Yes-No): -2.959 (Std.Error: 0.9)
Observational differences in treatment -3.96 (Yes-No)
treatment outcome
1: Yes 18.76625
2: No 22.72589`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Average Treatment Effects - Complications
- Complications Type: Primary
- Reoperation Due to Complication: Yes
Outcome: complication
Distribution:
Proportion
0.2939759
Model Type Y: boosting
Accuracy: 0.577777777777778
Params: nrounds: 50.0
max_depth: 4
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.716232506479082
Params: nrounds: 50.0
max_depth: 1
eta: 0.4
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): 0.142 (Std.Error: 0.044)
Trimmed ATE (Yes-No): 0.141 (Std.Error: 0.046)
Upper ATE (Yes-No): 0.159 (Std.Error: 0.073)
Observational differences in treatment 0.044 (Yes-No)
treatment outcome
1: Yes 0.3333333
2: No 0.2891892`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: Mechanical complications
Distribution:
Proportion
0.2120482
Model Type Y: boosting
Accuracy: 0.801666666666667
Params: nrounds: 50.0
max_depth: 5
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.789189189189189
Params: nrounds: 100.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): -0.068 (Std.Error: 0.025)
Trimmed ATE (Yes-No): -0.076 (Std.Error: 0.025)
Upper ATE (Yes-No): 0.157 (Std.Error: 0.06)
Observational differences in treatment -0.014 (Yes-No)
treatment outcome
1: Yes 0.2000000
2: No 0.2135135`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: Infectious complications
Distribution:
Proportion
0.06024096
Model Type Y: boosting
Accuracy: 0.913333333333333
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.943275330124645
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): 0.069 (Std.Error: 0.019)
Trimmed ATE (Yes-No): 0.071 (Std.Error: 0.02)
Upper ATE (Yes-No): 0.009 (Std.Error: 0.014)
Observational differences in treatment 0.032 (Yes-No)
treatment outcome
1: Yes 0.08888889
2: No 0.05675676`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: Peripheral neurologic complications
Distribution:
Proportion
0.04819277
Model Type Y: boosting
Accuracy: 0.913333333333333
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.956789830926817
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): 0.143 (Std.Error: 0.033)
Trimmed ATE (Yes-No): 0.152 (Std.Error: 0.035)
Upper ATE (Yes-No): -0.101 (Std.Error: 0.035)
Observational differences in treatment 0.046 (Yes-No)
treatment outcome
1: Yes 0.08888889
2: No 0.04324324`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Outcome: Other complications
Distribution:
Proportion
0.0626506
Model Type Y: boosting
Accuracy: 0.913333333333333
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.940572627421942
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.6
min_child_weight: 1.0
subsample: 0.5
ATE (Yes-No): 0.027 (Std.Error: 0.018)
Trimmed ATE (Yes-No): 0.03 (Std.Error: 0.018)
Upper ATE (Yes-No): -0.04 (Std.Error: 0.031)
Observational differences in treatment 0.029 (Yes-No)
treatment outcome
1: Yes 0.08888889
2: No 0.05945946`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Average Treatment Effects - Reintervention Number
Outcome: reinterventions
Distribution:
0% 25% 50% 75% 100%
0 0 0 1 6
Model Type Y: boosting
RMSE: 1.47342708159134
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5714286
Model Type No: boosting
RMSE: 0.914686702660187
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.7142857
ATE (Yes-No): 0.032 (Std.Error: 0.093)
Trimmed ATE (Yes-No): 0.089 (Std.Error: 0.097)
Upper ATE (Yes-No): -1.483 (Std.Error: 0.128)
Observational differences in treatment 0.135 (Yes-No)
treatment outcome
1: No 0.4648649
2: Yes 0.6000000`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
Average Treatment Effects - Had Reintervention
Outcome: had_reintervention
Distribution:
Proportion
0.2963855
Model Type Y: boosting
Accuracy: 0.660555555555556
Params: nrounds: 50.0
max_depth: 7
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.5
Model Type No: boosting
Accuracy: 0.708123411082315
Params: nrounds: 50.0
max_depth: 1
eta: 0.3
gamma: 0.0
colsample_bytree: 0.8
min_child_weight: 1.0
subsample: 0.7142857
ATE (Yes-No): 0.053 (Std.Error: 0.04)
Trimmed ATE (Yes-No): 0.049 (Std.Error: 0.041)
Upper ATE (Yes-No): 0.163 (Std.Error: 0.059)
Observational differences in treatment 0.017 (Yes-No)
treatment outcome
1: Yes 0.3111111
2: No 0.2945946`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'
`geom_smooth()` using formula 'y ~ x'